Computer Science and Artificial Intelligence Laboratory (CSAIL)

In a forest simulation, algorithms segment space into “obstacle-free regions” and then link them together to find a single collision-free route.

Drones dodge obstacles

Motion-planning algorithms allow drones to do donuts, figure-eights in object-filled environments.

January 19, 2016

“It started informally as my way of giving back to the MIT community,” says MIT junior Benjamin Chan. His daily chalkboard project welcomes students, faculty, staff, and visitors to the Stata Center.

Mind, hand, heart — and chalk

A daily art project conceived by MIT student Benjamin Chan welcomes students, faculty, staff, and visitors to the Stata Center.

January 13, 2016

MIT affiliates were well represented in the 2016 Forbes 30 Under 30, honoring young leaders.

25 from MIT named to Forbes 30 Under 30 lists in 2016

Students, researchers, and alumni honored in the 2016 Forbes 30 Under 30 lists showcasing America’s most important young entrepreneurs, thinkers, and leaders.

January 7, 2016

This image demonstrates tissue patterns that emerge from genetically programmed human pluripotent stem cells, and was taken on day nine of the MIT study. It shows immunostainings of cell nuclei for CEBPA (red, endodermal marker), SOX10 (green, ectodermal marker), and DAPI (blue, binds to DNA in the nucleus).

Organ-on-a-chip

In a step toward personalized drug testing, researchers coax human stem cells to form complex tissues.

January 6, 2016

The DriveWell app runs in the background of a smartphone, collecting data on driving behavior. Drivers receive a score on a scale from 1 to 100, a route map, and tips for improvement. Scores can also be used for insurance discounts, or to compete with friends and other drivers worldwide.

Smarter driving, using your phone

App that rates drivers’ behavior yields promising safety results on the road.

January 5, 2016

MIT researchers fed their physics prediction system videos of collisions, shown as screenshots in (a) and (b), which were then converted into simulations generated by the 3-D physics engine, shown in (c) and (d).

Computer model matches humans at predicting how objects move

“3-D physics engine” from the Computer Science and Artificial Intelligence Laboratory simulates the human brain to infer physical properties.

January 4, 2016

Researchers have developed a computational model of visual representation intended to reflect the way the brain works.

Machines that learn like people

Algorithms could learn to recognize objects from a few examples, not millions; may better model human cognition.

December 23, 2015

“In health care, there’s this gigantic world of unstructured data that needs to be translated into useable information,” says Paul Nemirovsky, who co-founded dMetrics with Ariadna Quattoni.

Detecting consumer decisions within messy data

Software analyzes online chatter to predict health care consumers’ behavior.

December 21, 2015

For each image, the MemNet algorithm creates a heat map identifying its most memorable and forgettable regions.

Deep-learning algorithm predicts photos’ memorability at “near-human” levels

Future versions of an algorithm from the Computer Science and Artificial Intelligence Lab could help with teaching, marketing, and memory improvement.

December 16, 2015